Scientific Reasoning

Follow this topic Ask about this topic

Scientific reasoning asks whether AI can move from evidence to sound explanations, predictions, and testable hypotheses—not just produce plausible answers. Approaches include language-model reasoning traces, retrieval and tool-using agents, domain-specific fine-tuning, and process reward models that check intermediate steps; multimodal systems also work with figures, images, and structured scientific data. Evaluations range from physics and chemistry problems to interactive research tasks that test evidence gathering, tool use, and hypothesis generation. Models are improving on structured problems, but reliable evidence integration, mechanistic reasoning, and distinguishing genuine inference from memorized knowledge remain open challenges.

Latest papers

45 papers1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

ChemExplain: A Multimodal Benchmark for Explanatory Chemical Reasoning
Oct 12, 2026Aotian Chen, Frazier N. Baker, Reza Averly +5Scientific Reasoning Explainability Evaluation
The Ohio State University · Adelaide University
Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents
Sep 10, 2026Jiaqiang Li, Yajie Yang, Zhiheng Xi +15Evidence-Grounded Reasoning Scientific Reasoning
Fudan NLP Lab · Fudan NLP Group
ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad Competitions
Aug 31, 2026Guangxiang Zhao, Qilong Shi, Xusen Xiao +13LLM Evaluation Scientific Reasoning
1Qiyuan Tech · 2Tsinghua University · 3The University of Hong Kong +1
SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature
Aug 31, 2026Yu Li, Wei Li, Xin Gao +4Evidence-Grounded Reasoning Scientific Reasoning
Shanghai AI Laboratory · University of Science and Technology of China · 1Shanghai AI Laboratory 2University of Science and Technology of China +5
Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning
Aug 25, 2026Zhen Bi, Xueshu Chen, Yan Wang +6Memory-Augmented Language Models Scientific Reasoning
Huzhou Normal University · Alibaba Group · Bota Biosciences +1
Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking
Aug 18, 2026Swati Rajwal, Sanjay Das, Tirthankar GhosalScientific Idea Evaluation Large Language Model-Guided Scientific Discovery
Oak Ridge National Laboratory
Pessimistic Meta-Induction and Its Limits: Lessons from Frequentist Statistics and Machine Learning Theory
Aug 17, 2026Hanti LinInductive Inference Scientific Reasoning
University of California, Davis
MUSE: A Full-Text Cross-Domain Knowledge Base of Scientific Problems, Solutions, and Rationales
Aug 11, 2026Tsofia Cohen, Tom HopeRelation Extraction KG Construction
The Hebrew University of Jerusalem · Allen Institute for AI (Ai2)
Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery
Aug 7, 2026Taolin Han, Yuchen Zhang, Jinghang Wang +22Scientific Reasoning Scientific Discovery
1Alibaba Group · University of Chinese Academy of Sciences · Taolin Han1,3* +28
Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad
Jul 23, 2026Jiatong Li, Yuxuan Ren, Weida Wang +2CoT Faithfulness Chemical Reasoning in LLMs
Blue Whale Lab, National University of Singapore · Fudan University · Hong Kong Polytechnic University
Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation
Jul 18, 2026Mingqiao Mo, Yunlong Tan, Hao ZhangLLM Self-Correction Scientific Reasoning
University of Chinese Academy of Sciences
Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists
Jul 13, 2026Chuhan Shi, Xiaoquan Ren, Sicheng Song +3AI for Science LLM Evaluation
Southeast University · East China Normal University · Hong Kong University of Science and Technology
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Jul 9, 2026Yifan Zhou, Qihao Yang, Yan Li +14Scientific Reasoning Scientific Hypothesis Generation
Shanghai Jiao Tong University · Carnegie Mellon University · University of Chinese Academy of Sciences +4
A safety-oriented hypothetico-deductive framework for AI-assisted differential diagnosis
Jul 9, 2026Fan Ma, Mauro Giuffrè, Donald Wright +12Scientific Reasoning Medical Diagnosis
Department of Biomedical Informatics and Data Science, Yale School of Medicine, Yale University, New Haven, USA · Department of Medical, Surgical and Health Sciences, Università degli Studi di Trieste, Trieste, Italy · Department of Emergency Medicine, Yale School of Medicine, Yale University, New Haven, USA +3
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Jul 8, 2026Chen Tang, Yizhou Wang, Jianyu Wu +26Scientific Reasoning Materials Property Prediction
Shanghai Artificial Intelligence Laboratory, China. · The Chinese University of Hong Kong, Hong Kong. · Shanghai Jiao Tong University, China. +8
IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs
Jul 1, 2026Samir Abdaljalil, Erchin Serpedin, Hasan KurbanLLM Evaluation Scientific Reasoning
Electrical and Computer Engineering Texas A&M University College Station, TX USA · College of Science and Engineering Hamad Bin Khalifa University Doha, Qatar
Accelerating Returns and the Qualitative Engine for Science
Jun 24, 2026Guojun LiaoAI for Science Scientific Reasoning
Department of Mathematics, The University of Texas at Arlington · Department of Mathematics, University of Texas at Arlington
SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding
Jun 18, 2026Yueming Wang, Tianshi Zheng, Jiaxin Bai +3Multimodal Grounding AI for Science
The Hong Kong University of Science and Technology Hong Kong SAR, China · NVIDIA AI Technology Center Santa Clara, USA
A Three-Layer Framework for AI in Scientific Discovery
Jun 11, 2026Guojun LiaoAI for Science Scientific Reasoning
Department of Mathematics, University of Texas at Arlington
TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data?
Jun 11, 2026Dat Tien Nguyen, Thao Nguyen, Fadillah Adamsyah Maani +5Spatial Reasoning Scientific Reasoning
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · ADIA Lab, Abu Dhabi, UAE
SciR: A Controllable Benchmark for Scientific Reasoning in LLMs
Jun 11, 2026Pierre Beckmann, Marco Valentino, Andre FreitasLLM Evaluation Scientific Reasoning
Idiap Research Institute, Switzerland · EPFL, Switzerland · School of Computer Science, University of Sheffield, UK +2
DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations
Jun 7, 2026Lei Lin, Ronghao Wang, Chunbao Zhou +2Scientific Reasoning Scientific Hypothesis Generation
Computer Network Information Center, Chinese Academy of Sciences, China
Contemporary AI lacks the imagination to diverge or negate in science
Jun 6, 2026Honglin Bao, Siyang Wu, Xiao Liu +3LLM-as-a-Judge Scientific Reasoning
Data Science Institute, University of Chicago · Knowledge Lab, University of Chicago
SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification
Jun 3, 2026Xiangyu Zhao, Henry Hengyuan Zhao, Yiheng Wang +7Process Reward Models Scientific Reasoning
The Hong Kong Polytechnic University · National University of Singapore · Shanghai AI Lab +3
NewtPhys: Do Foundation Models Understand Newtonian Physics?
Jun 2, 2026Sebastian Cavada, Soumava Paul, Tuan-Hung Vu +2VLM Evaluation Scientific Reasoning
MBZUAI · Inria
Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery
May 31, 2026Zhe Zhao, Haibin Wen, Yingcheng Wu +10Multi-Agent Coordination Multi-Agent Orchestration
Department of Pathology, Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA · Scripps Research, La Jolla, CA, USA · Division of Biostatistics, Department of Population Health, New York University Grossman School of Medicine, New York, NY, USA +4
Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches
May 31, 2026Teddy Ferdinan, Bartłomiej Koptyra, Mikołaj Langner +42AI for Science Scientific Reasoning
ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure
May 28, 2026A. J. Lew, Y. Cao, M. J. BuehlerLLM Evaluation Scientific Reasoning
Unreasonable Labs · Unreasonable Labs Mountain View, CA 94043, USA
On the evolution of the concept of probability as a mirror of the evolution of reason
May 26, 2026Jean-Louis Le Mouël, Vincent Courtillot, Dominique Gibert +6Scientific Reasoning Epistemic Uncertainty
Acad´emie des Sciences, Institut de France, Paris, France · DeepField Sensing, France · Institute of Earthquake Prediction Theory and Mathematical Geophysics, Russian Academy of Sciences, Moscow, Russia +4
Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning
May 24, 2026Chenyou Guo, Zongqi Liu, Yizhou Zhang +2Scientific Reasoning LLM Fine-Tuning
Ocean University of China · Peking University · Monash University

Oct 12, 2026J/K move · Enter open · S save

ChemExplain: A Multimodal Benchmark for Explanatory Chemical Reasoning

Aotian Chen, Frazier N. Baker, Reza Averly, Shan Zhang+4

The Ohio State University · Adelaide University

Scientific Reasoning Explainability Evaluation Scientific QA Multimodal Reasoning

Open paper AskPDF arXiv

Current chemistry benchmarks primarily evaluate outcome prediction or reaction pathway generation, but rarely test whether a model can explain why an observed chemical effect occurs. We introduce ChemExplain, a benchmark of 1,180 multiple-choice chemistry questions drawn from 383 peer-reviewed papers. Each question pairs a molecular or reaction image with an observed chemical effect and four candidate explanations, each associated with a different structural feature visible in the image. Answering requires the model to perceive the depicted structure, apply chemical knowledge, and identify which feature most directly explains the effect, a capability we term explanatory attribution. The correct feature-mechanism relation is derived from supporting evidence in the source paper rather than invented by the question-generation LLM. We construct the benchmark automatically with a multi-agent framework that applies progressive quality control at three stages and validate it with eight chemistry domain experts. The strongest evaluated model reaches 78.6% accuracy, leaving considerable room for improvement. On a 600-question expert-reviewed subset, reasoning-trace analysis classifies 71.4% of the strongest model's errors as attribution failures. Attribution is also the largest error category for the open-source and chemistry-specific models included in our analysis.